Transcribe audio using huggingface #1718
Merged
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Background
Addition of a audio transcriber command that uses the huggingface inference API to call an audio to text model.
Changes
Added a new python file called audio_text.py that contains the read_audio function, which call the huggingface API.
Made changes to prompt.py, the env template, config.py, and app.py to include the read_audio function and make it functional.
Documentation
The changes are implemented as just in code comments.
Test Plan
I tested the changes by added various audio samples to the working directory. Then I asked the agent to transcribe the audio samples and compare the transcribed stories to each other.
PR Quality Checklist